Hello,
first time trying this so bare with me please and sorry if I don't really get the instructions..
I am not really sure what to do with the manual transform though is there something I need to enter in the SfMTransform (manual) Translation x y z or Euler Rotation? I left everything to 0 in doubt.

2023-07-30 00:39:07 | INFO | font_manager.py : 1544 | >>> generated new fontManager
2023-07-30 00:39:10 | WARNING | mr2nerf.py : 109 | >>> W/H ratio does not match sensor ratio, this is likely a bug from Meshroom. Will use fl_x to set fl_y.
Traceback (most recent call last):
File "C:\Users\Shady\Documents\mr2nerf\mr2nerf.py", line 226, in
camera['transform_matrix'] = transforms[poseId]
~~~~~~~~~~^^^^^^^^
KeyError: '137075643'

Dear joreeves

I tried to use your script but did not arrive at the expected result. I generated camera postions from 17 pictures in Meshroom via the StructureFromMotion node. I exported this to a json file via the ConvertSfMFormat node per your instructions. I then ran your script to generate the transforms.json file and arrived at following results.
As example 1 of 17 source pictures:

Results:

I got these messages when I ran the script:

The dense point cloud I generated from Meshroom some nodes down the line however seems perfectly fine so I do not really doubt the correctness of the generated camerapositions, not in Meshroom and also not in your script as can be seen above in the InstantNGP screenshots.

Then I tested to generate the transforms.json file anew via the instantngp-batch procedure described over here:
https://github.com/jonstephens85/instantngp-batch
The procedure first runs colmap to detect camera postions anew and then uses the script colmap2nerf.py to generate the transfroms.json file. This procedure yields significantly better results. See below.

However, I have needed to calculate the camerapositions twice now, once in Meshroom and once via Colmap. I would prefer to only do this once and see promise for your script if it would yield the same results as the Colmap procedure.
I was wondering if there maybe could be a bug somewhere in your script? For example, I see that the considered volume that the neural network calculates is considerably larger when using the transforms.json file generated by your script compared to the volume used by the colmap generated transforms.json file.
Looking forward to any answer you can give. Please let me know if you need any of my testfiles. I am more than happy to provide those.

For your convenience I have already included both transforms.json files generated by Colmap and by Meshroom and your script:
transforms_FromColmap.json.txt
transforms_FromMeshroom.json.txt

Kind regards
Paulus

not use meshroom gui, use cli instead
for example, meshroom_batch

Focal Lengths in the output transforms.json came out like so:

"fl_x": 3282.2516711791563,
"fl_y": 5842.794435803687,

For the dataset I was testing "fl_x" looked right, but usually "fl_y" is the same value so it seemed strange. When testing in intant-ngp in never converged. When I manually set "fl_y" to the same value it converged.

Looking at the sfm.json I generated from meshroom it looks like there's only a single value for focal length (I assume in millimeters). Is the script converting based on this value and scaling based on image dimensions?